AU2018256505B2 - Artificial intelligence system for providing road surface risk information and method thereof - Google Patents
Artificial intelligence system for providing road surface risk information and method thereof Download PDFInfo
- Publication number
- AU2018256505B2 AU2018256505B2 AU2018256505A AU2018256505A AU2018256505B2 AU 2018256505 B2 AU2018256505 B2 AU 2018256505B2 AU 2018256505 A AU2018256505 A AU 2018256505A AU 2018256505 A AU2018256505 A AU 2018256505A AU 2018256505 B2 AU2018256505 B2 AU 2018256505B2
- Authority
- AU
- Australia
- Prior art keywords
- road
- information
- basis
- learning
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
[66] Disclosed is an artificial intelligence system for providing road risk information and a method thereof. The system for providing road risk information according to an embodiment of 5 the present invention comprises: an information collection unit for receiving various road state information acquired from a vehicle device; an information processing unit for performing image processing on the collected road state information, and converting a result of the image processing into a predefined 10 grayscale image; an information learning unit for learning the converted predefined grayscale image on the basis of a predetermined learning model based on deep learning, and recognizing the road risk information on the basis of a result of the learning; and an information classification unit for 15 classifying the road risk information from the road state information on the basis of a result of the recognition, and detecting road surface defects on the basis of a result of the classification.
Description
ARTIFICIAL INTELLIGENCE SYSTEM FOR PROVIDING ROAD SURFACE
2018256505 12 Mar
RISK INFORMATION AND METHOD THEREOF
TECHNICAL FIELD [01] The present disclosure to a road risk information classification system, and more specifically, to a system and method for classifying road risk information on the basis of deep learning .
BACKGROUND [02] Generally, a road that is prepared for driving of vehicles is constructed using a material such as asphalt, concrete or the like, and various types of road surface markings for guiding driving of vehicle drivers, as well as lines for dividing driving paths, are formed on the road surface. At this point, the road surface markings include turn-left, turn-right and go-straight arrows, markings of destination names, speed limit markings, crosswalk markings and the like.
[03] Although vehicle drivers reach a destination with the help of the road surface markings and road signs like this in the past, recent vehicle drivers drive with the guidance of a navigation device installed in a vehicle to further quickly and conveniently reach the destination. A general navigator provided with a display implements various functions, such as guiding routes
2018256505 12 Mar to a destination, alarming speed limits, displaying rest areas and gas stations and the like, for comfortable driving of a vehicle driver .
[04] However, since the navigator is merely an apparatus which recognizes a road as a simply line and guides a route on the basis of a map, it may not provide intuitive guidance on a state of a road. For example, when traffic lanes or road surface markings are erased and difficult to identify or roads are damaged to have cracks or potholes, if the drivers rely only on the navigator, the risk of occurring an accident may greatly increase due to the bad condition of the roads. Accordingly, a system that can also provide practical guidance on the road states, in addition to simple guidance on the routes using the navigator, is required to solve the problem.
[05] It is desired to address or ameliorate one or more disadvantages or limitations associated with the prior art, or to at least provide a useful alternative.
SUMMARY [06] In accordance with the present disclosure, there is provided a system for classifying road risk information, the system comprising :
2018256505 12 Mar an information collection unit for receiving various road state information acquired from a vehicle device;
an information processing unit for performing image processing on the collected road state information by extracting a polygonal Region of Interest (ROI) from a road image among the collected road state information, performing image processing on the extracted ROI, and creating a grayscale image on the basis of a result of the image processing;
an information learning unit for learning the created grayscale image on the basis of a predetermined learning model based on deep learning, and recognizing the road risk information on the basis of a result of the learning; and an information classification unit for classifying the road risk information from the road state information on the basis of a result of the recognition, and detecting road surface defects on the basis of a result of the classification.
[07] In an alternative embodiment, there is provided a system for classifying road risk information, the system comprising:
a communication unit for collecting various road state information acquired from a vehicle device;
a control unit for learning the collected road state information on the basis of a predetermined learning model based on deep learning, classifying the road risk information from the road state information on the basis of a result of the learning,
2018256505 12 Mar and detecting road surface defects on the basis of a result of the classification; and a storage unit for storing the collected road state information, the predetermined learning model, and the classified road risk information, wherein the control unit activates a mobile application, performs image processing on the collected road state information through the activated mobile application, converts a result of the image processing into a grayscale image, and learns the converted grayscale image on the basis of a predetermined learning model based on deep learning; and wherein the image processing involves the control unit extracting a Region of Interest (ROI) from a road image among the collected road state information, and performing image processing on the extracted ROI.
[08] In a further alternative embodiment, there is provided a method of classifying road risk information, the method comprising :
an information collection step of receiving various road state information acquired from a vehicle device;
an information processing step of performing image processing by extracting a Region of Interest (ROI) from a road image among the collected road state information, performing image processing
2018256505 12 Mar on the extracted ROI, and creating a grayscale image on the basis of a result of the image processing;
an information learning step of learning the created grayscale image on the basis of a predetermined learning model based on deep learning, and recognizing the road risk information on the basis of a result of the learning; and an information classification step of classifying the road risk information from the road state information on the basis of a result of the recognition, and detecting road surface defects on the basis of a result of the classification.
BRIEF DESCRIPTION OF THE DRAWINGS [09] FIG. 1 is a view showing a system for classifying road risk information according to an embodiment of the present disclosure .
[10] FIG. 2 is a view showing the configuration of the service server shown in FIG. 1.
[11] FIG. 3 is a flowchart illustrating a method of classifying road risk information according to an embodiment of the present disclosure.
[12] FIG. 4 is a view showing a system for classifying road risk information according to another embodiment of the present disclosure .
2018256505 12 Mar [13] FIG. 5 is a view showing the configuration of the mobile device shown in FIG. 4.
DESCRIPTION OF SYMBOLS
100: Vehicle device
200: User device
300: Service server
400: Database [14] The present disclosure has been made in view of the above problems, and it provides a system and method for classifying road risk information on the basis of deep learning, which collects road state information photographing a driving road, learns the collected road state information on the basis of a learning model based on deep learning, and classifies road risk information on the basis of a result of the learning.
[15] According to one aspect of the present disclosure, there is provided a system for classifying road risk information, the system comprising: an information collection unit for receiving various road state information acquired from a vehicle device; an information processing unit for performing image processing on the collected road state information, and converting a result of the
2018256505 12 Mar image processing into a predefined grayscale image; an information learning unit for learning the converted predefined grayscale image on the basis of a predetermined learning model based on deep learning, and recognizing the road risk information on the basis of a result of the learning; and an information classification unit for classifying the road risk information from the road state information on the basis of a result of the recognition, and detecting road surface defects on the basis of a result of the classification.
[16] In addition, the information processing unit may extract a polygonal Region of Interest (ROI) from a road image among the collected road state information, perform image processing on the extracted ROI, and create a predefined grayscale image on the basis of a result of the image processing.
[17] In addition, the information learning unit may learn the converted predefined grayscale image on the basis of at least two predetermined learning models based on deep learning.
[18] In addition, the system for classifying road risk information may further comprise an information transmission unit for transmitting the road surface defects detected by the information classification unit to the user device.
[19] According to another aspect of the present disclosure, there is provided a system for classifying road risk information, the system comprising: a communication unit for collecting various
2018256505 12 Mar road state information acquired from a vehicle device; a control unit for learning the collected road state information on the basis of a predetermined learning model based on deep learning, classifying the road risk information from the road state information on the basis of a result of the learning, and detecting road surface defects on the basis of a result of the classification; and a storage unit for storing the collected road state information the predetermined learning model, and the classified road risk information .
[20] In addition, the control unit may activate a mobile application, perform image processing on the collected road state information through the activated mobile application, convert a result of the image processing into a predefined grayscale image, and learn the converted predefined grayscale image on the basis of a predetermined learning model based on deep learning.
[21] In addition, the control unit may extract a Region of Interest from a road image among the collected road state information, perform image processing on the extracted ROI, and create a predefined grayscale image on the basis of a result of the image processing.
[22] In addition, the control unit may recognize the road risk information on the basis of a result of the learning, classify the road risk information from the road state information on the basis of a result of the recognition, and detect road surface
2018256505 12 Mar defects on the basis of a result of the classification.
[23] According to still another aspect of the present disclosure, there is provided a method of classifying road risk information, the method comprising: an information collection step of receiving various road state information acquired from a vehicle device; an information processing step of performing image processing on the collected road state information, and converting a result of the image processing into a predefined grayscale image; an information learning step of learning the converted predefined grayscale image on the basis of a predetermined learning model based on deep learning, and recognizing the road risk information on the basis of a result of the learning; and an information classification step of classifying the road risk information from the road state information on the basis of a result of the recognition, and detecting road surface defects on the basis of a result of the classification.
[24] In addition, the information processing step may extract a Region of Interest (ROI) from a road image among the collected road state information, perform image processing on the extracted ROI, and create a predefined grayscale image on the basis of a result of the image processing.
ADVANTAGEOUS EFFECTS
2018256505 12 Mar [25] The present disclosure may detect road surface defects by collecting road state information photographing a driving road, learning the collected road state information on the basis of a learning model based on deep learning, and classifying road risk information on the basis of a result of the learning.
[26] In addition, since the present system is able to extract road surface defects using artificial intelligence based on deep learning, traffic accidents can be prevented.
[27] In addition, since the present system learns the road state information on the basis of artificial intelligence based on deep learning and classifies road risk information on the basis of a result of the learning, reliability of information can be enhanced.
[28] However, the effects of the present disclosure are not limited to the effects as described above, but may be diversely expanded without departing from the spirit and scope of the present disclosure .
[29] The embodiments will be described in detail as sufficient as to be embody the present disclosure by those skilled in the art. It should be understood that diverse embodiments of the present disclosure do not need to be mutually exclusive although they are different from each other. For example, the specific shapes, structures and characteristics disclosed herein may be implemented in other embodiments in relation to an
2018256505 12 Mar embodiment without departing from the spirit and scope of the present disclosure. In addition, it should be understood that the positions or arrangements of individual components in each disclosed embodiment can be changed without departing from the spirit and scope of the present disclosure. Accordingly, the detailed description described below is not intended to be taken as a restrictive meaning, but if it is properly described, the scope of the present disclosure is restricted only by the appended claims, together with all scopes equivalent to the claims. In the drawings, the similar reference symbols refer to the same or similar functions throughout several aspects.
[30] Hereinafter, a system and method for classifying road risk information on the basis of deep learning according to an example embodiment of the present disclosure will be described with reference to the accompanying drawings. Particularly, the present disclosure proposes a new method of detecting road surface defects on the basis of road risk information by collecting road state information photographing a driving road, learning the collected road state information on the basis of a learning model based on deep learning, and classifying the road risk information on the basis of a result of the learning.
[31] FIG. 1 is a view showing a system for classifying road risk information according to an embodiment of the present disclosure .
2018256505 12 Mar [32] Referring to FIG. 1, a system for classifying road risk information according to an embodiment of the present disclosure may include a vehicle device 100, a user device 200, a service server 300 and a database 400.
[33] The vehicle device 100 is attached to a vehicle and may acquire various road state information, such as road images, sensing values and the like, from a road on which the vehicle is running. The vehicle device 100 may include a camera for acquiring the road images, and a sensor for acquiring the sensing values. The vehicle device 100 may connect to the user device 200 through wireless communication and provide the user device 200 with various types of acquired information.
[34] The user device 200 may connect to the vehicle device 100 through wireless communication, collect various road state information, and transfer the collected various road state information to the service server 300.
[35] The service server 300 may connect to the user device 200 through wireless communication, receive various road state information, learn the received road state information on the basis of deep learning, classify the road risk information on the basis of a result of the learning, and detect road surface defects on the basis of the classified road risk information. The road risk information may include, for example, potholes, fallen objects, cracks, black ice, damage of lanes and the like. Here, the pothole is a local small hole formed on the pavement surface when the
2018256505 12 Mar asphalt pavement is commonly used.
[36] In addition, the deep learning algorithm refers to a technique used to allow a computer to make a decision and learn like a human being and to cluster or classify objects or data through the computer. For example, the deep learning algorithm includes Deep Neural Network (DNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM) and the like.
[37] The database 400 may store and manage the collected road state information, at least one predefined learning model, and the road risk information classified through the learning model.
[38] FIG. 2 is a view showing the configuration of the service server shown in FIG. 1.
[39] Referring to FIG. 2, the service server 300 according to an embodiment of the present disclosure may include an information collection unit 310, an information processing unit 320, an information learning unit 330, an information classification unit 340 and an information transmission unit 350.
[40] The information collection unit 310 may connect to the user device through wireless communication and collect various road state information. The object of the information collection unit is collecting road state information, and the information collection unit collects unclassified abnormal road state
2018256505 12 Mar information .
[41] The information processing unit 320 may extract a Region of Interest (ROI) from a road image among the collected road state information, perform image processing on the extracted ROI, and create a predefined grayscale image on the basis of a result of the image processing. Although all the road images may be used in the present disclosure, only the ROI may be converted and used as a predefined grayscale image for effective utilization of system resources. In addition, the ROI is set in a variety of forms. The ROI is set in a polygonal form, such as a rectangular or trapezoidal form, by adjusting the outer line of the ROI in a direction parallel to the lanes by utilizing a sense of perspective.
[42] The information learning unit 330 may learn the converted predefined grayscale image on the basis of a learning model based on deep learning, and recognize road risk information on the basis of a result of the learning. A learning device compares the grayscale image with a reference image manufactured in advance.
[43] The information classification unit 340 may classify the road risk information, for example, potholes and non-potholes, from the road state information on the basis of a result of the recognition, and detect road surface defects. In addition, the information classification unit 340 classifies the non-potholes in
2018256505 12 Mar detail according to road damage types, such as labeling, turtle crack, lateral or traversal damage, spalling and the like, and also classifies features other than those of the road pavement surface, such as objects fallen on the road, skid marks, manholes and the like .
[44] The information transmission unit 350 may transmit the detected road surface defects to the user device.
[45] FIG. 3 is a flowchart illustrating a method of classifying road risk information according to an embodiment of the present disclosure.
[46] Referring to FIG. 3, a method of classifying road risk information according to an embodiment of the present disclosure may include an information collection step S310, an information processing step S320, an information learning step S330, an information classification step S340, and an information transmission step S350.
[47] The information collection step S310 may be provided with various road state information acquired from the vehicle device .
[48] The information processing step S320 may perform image processing on the collected road state information and convert a result of the image processing into a predefined grayscale image.
[49] The information learning step S330 may learn the converted predefined grayscale image on the basis of a
2018256505 12 Mar predetermined learning model based on deep learning, and recognize road risk information on the basis of a result of the learning.
[50] The information classification step S340 may classify the road risk information from the road state information on the basis of a result of the recognition, and detect road surface defects on the basis of a result of the classification.
[51] The information transmission step S350 may transmit the detected road surface defects to the user device.
[52] FIG. 4 is a view showing a system for classifying road risk information according to another embodiment of the present disclosure .
[53] Referring to FIG. 4, a system for classifying road risk information according to another embodiment of the present disclosure may include a vehicle device 100, a user device 200, a service server 300, and a database 400.
[54] The vehicle device 100 is attached to a vehicle and may acquire various road state information, such as road images, sensing values and the like, from a road on which the vehicle is running. The vehicle device 100 may include a camera for acquiring the road images, and a sensor for acquiring the sensing values. The vehicle device 100 may connect to the user device 200 through wireless communication and provide the user device 200 with various types of acquired information.
2018256505 12 Mar [55] The user device 200 may activate a mobile application for detecting road surface defects, wirelessly connect to the vehicle device 100 through the activates mobile application, collect various road state information, learn the collected road state information on the basis of a learning model based on deep learning, classify road risk information on the basis of a result of the learning, and detect road surface defects on the basis of the classified road risk information.
[56] The service server 300 may connect to the user device 200 through wireless communication, provide the user device 200 with a mobile application for detecting road surface defects and at least one predefined learning model, and receive information on detected road surface defects from the user device 200.
[57] The database 400 may store and manage the collected road state information, at least one predefined learning model, and the road risk information classified through the learning model.
[58] FIG. 5 is a view showing the configuration of the mobile device shown in FIG. 4.
[59] Referring to FIG. 5, a mobile device 200 according to another embodiment of the present disclosure may include a communication unit 210, an input unit 220, a control unit 230, a display unit 240, and a storage unit 250.
[60] The communication unit 210 may connect to the vehicle device 100 and the service server 300 and transmit and receive
2018256505 12 Mar various information. For example, the communication unit 210 may connect to the vehicle device 100 and collect various road state information. As another example, the communication unit 210 may connect to the service server 300 to be provided with a mobile application for detecting road surface defects and information on detected load surface defects.
[61] The input unit 220 may receive information from the user according to handling of a menu or a key.
[62] The control unit 230 may extract a Region of Interest (ROI) from a road image among the collected road state information, perform image processing on the extracted ROI, and create a predefined grayscale image on the basis of a result of the image processing .
[63] The control unit 230 may learn the converted predefined grayscale image on the basis of a learning model based on deep learning, and recognize road risk information on the basis of a result of the learning.
[64] The control unit 230 may classify the road risk information, for example, potholes and non-potholes, from the road state information on the basis of a result of the recognition, and detect road surface defects.
[65] The display unit 240 may display various information on the detected road surface defects.
2018256505 12 Mar [66] The storage unit 250 may store and manage the collected road state information, at least one predefined learning model, and the road risk information classified through the learning model.
[67] The features, structures, effects and the like described in the above embodiments are included in one embodiment of the present dislosure, and they are not necessarily limited to one embodiment. Furthermore, the features, structures, effects and the like exemplified in each embodiment may be embodied to be combined with or modified respect to other embodiments by those skilled in the art. Accordingly, contents related to the combination and modification should be interpreted as being included in the scope of the present disclosure.
[68] Although it has been described focusing on the embodiments, this is only illustrative and not intended to restrict the present disclosure, and those skilled in the art may make various modifications and applications that have not been described above without departing from the original features of the embodiments. For example, each constitutional component specifically shown in the embodiments may be modified to be embodied. In addition, the differences related to the modifications and applications should be interpreted as being included in the scope of the present disclosure specified in the appended claims .
2018256505 12 Mar [69] Throughout this specification and the claims which follow, unless the context requires otherwise, the word comprise, and variations such as comprises and comprising, will be understood to imply the inclusion of a stated integer or step or group of integers or steps but not the exclusion of any other integer or step or group of integers or steps.
[70] The reference in this specification to any prior publication (or information derived from it), or to any matter which is known, is not, and should not be taken as an acknowledgment or admission or any form of suggestion that that prior publication (or information derived from it) or known matter forms part of the common general knowledge in the field of endeavour to which this specification relates.
Claims (7)
1. A system for classifying road risk information, the system comprising:
5 an information collection unit for receiving various road state information acquired from a vehicle device;
an information processing unit for performing image processing on the collected road state information by extracting a polygonal Region of Interest (ROI) from a road image among the collected road 0 state information, performing image processing on the extracted ROI, and creating a grayscale image on the basis of a result of the image processing;
an information learning unit for learning the created grayscale image on the basis of a predetermined learning model 5 based on deep learning, and recognizing the road risk information on the basis of a result of the learning; and an information classification unit for classifying the road risk information from the road state information on the basis of a result of the recognition, and detecting road surface defects on 20 the basis of a result of the classification.
2. The system according to claim 1, wherein the information learning unit learns the converted predefined grayscale image on the basis of at least two predetermined learning models based on deep learning.
-21 2018256505
3. The system according to claim 1, further comprising an information transmission unit for transmitting the road surface defects detected by the information classification unit to the user
5 device.
4. A system for classifying road risk information, the system comprising:
a communication unit for collecting various road state
0 information acquired from a vehicle device;
a control unit for learning the collected road state information on the basis of a predetermined learning model based on deep learning, classifying the road risk information from the road state information on the basis of a result of the learning,
5 and detecting road surface defects on the basis of a result of the classification; and a storage unit for storing the collected road state information, the predetermined learning model, and the classified road risk information, wherein the control unit activates a mobile application,
20 performs image processing on the collected road state information through the activated mobile application, converts a result of the image processing into a grayscale image, and learns the converted grayscale image on the basis of a predetermined learning model based on deep learning; and
-22 2018256505 12 Mar wherein the image processing involves the control unit extracting a Region of Interest (ROI) from a road image among the collected road state information, and performing image processing on the extracted ROI.
5. The system according to claim 4, wherein the control unit extracts a Region of Interest from a road image among the collected road state information, performs image processing on the extracted ROI, and creates a predefined grayscale image on the
0 basis of a result of the image processing.
6. The system according to claim 4, wherein the control unit recognizes the road risk information on the basis of a result of the learning, classifies the road risk information from the road
5 state information on the basis of a result of the recognition, and detects road surface defects on the basis of a result of the classification.
7. A method of classifying road risk information, the 20 method comprising:
an information collection step of receiving various road state information acquired from a vehicle device;
an information processing step of performing image processing by extracting a Region of Interest (ROI) from a road image among
-23 2018256505 12 Mar the collected road state information, performing image processing on the extracted ROI, and creating a grayscale image on the basis of a result of the image processing;
an information learning step of learning the created grayscale
5 image on the basis of a predetermined learning model based on deep learning, and recognizing the road risk information on the basis of a result of the learning; and an information classification step of classifying the road risk information from the road state information on the basis of a 0 result of the recognition, and detecting road surface defects on the basis of a result of the classification.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020170174052A KR101969842B1 (en) | 2017-12-18 | 2017-12-18 | System for classifying dangerous road surface information based on deep running and method thereof |
| KR10-2017-0174052 | 2017-12-18 | ||
| PCT/KR2018/009043 WO2019124668A1 (en) | 2017-12-18 | 2018-08-08 | Artificial intelligence system for providing road surface danger information and method therefor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| AU2018256505A1 AU2018256505A1 (en) | 2019-07-04 |
| AU2018256505B2 true AU2018256505B2 (en) | 2020-04-30 |
Family
ID=66281584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2018256505A Active AU2018256505B2 (en) | 2017-12-18 | 2018-08-08 | Artificial intelligence system for providing road surface risk information and method thereof |
Country Status (3)
| Country | Link |
|---|---|
| KR (1) | KR101969842B1 (en) |
| AU (1) | AU2018256505B2 (en) |
| WO (1) | WO2019124668A1 (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091557B (en) * | 2019-12-12 | 2020-07-31 | 哈尔滨市科佳通用机电股份有限公司 | Method and system for detecting breakage fault of flange of bearing saddle of railway wagon |
| KR102494578B1 (en) * | 2020-12-09 | 2023-02-01 | 순천대학교 산학협력단 | Method and System for Artificial Intelligence based Quality Inspection in Manufacturing Process using Machine Vision Deep Learning |
| KR102244143B1 (en) * | 2020-12-17 | 2021-04-22 | 전남대학교산학협력단 | Apparatus for predicting accident and the control method thereof |
| KR102290548B1 (en) * | 2021-03-25 | 2021-08-13 | 전남대학교산학협력단 | Device and method for preventing traffic accident through judging road condition based on deep learning model |
| KR102452234B1 (en) * | 2022-01-24 | 2022-10-14 | 주식회사 백향우드 | IoT-based deck road management method that determines deck road damage by deep learning-based inference model |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6807473B1 (en) * | 2003-04-09 | 2004-10-19 | Continental Teves, Inc. | Road recognition system |
| US20160292518A1 (en) * | 2015-03-30 | 2016-10-06 | D-Vision C.V.S Ltd | Method and apparatus for monitoring changes in road surface condition |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010163131A (en) * | 2009-01-19 | 2010-07-29 | Sumitomo Electric Ind Ltd | Road surface state discriminating device |
| KR101060152B1 (en) | 2011-01-22 | 2011-08-29 | 인하대학교 산학협력단 | A method for observing road status using reconfigurable hardware |
| KR101453654B1 (en) * | 2013-02-19 | 2014-11-04 | 한국과학기술원 | Road condition recognition system and method for automobile safety |
| KR101501851B1 (en) * | 2013-11-28 | 2015-03-11 | 울산대학교 산학협력단 | Apparatus and method for lane detection using hough transformation at optimized accumulator cells |
| KR101797818B1 (en) * | 2015-10-26 | 2017-11-15 | 현대오토에버 주식회사 | Apparatus and method for providing road information based on deep learnig |
| KR101778724B1 (en) * | 2016-12-05 | 2017-09-14 | 동국대학교 산학협력단 | Device and method for reconition of road markings |
-
2017
- 2017-12-18 KR KR1020170174052A patent/KR101969842B1/en active IP Right Grant
-
2018
- 2018-08-08 AU AU2018256505A patent/AU2018256505B2/en active Active
- 2018-08-08 WO PCT/KR2018/009043 patent/WO2019124668A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6807473B1 (en) * | 2003-04-09 | 2004-10-19 | Continental Teves, Inc. | Road recognition system |
| US20160292518A1 (en) * | 2015-03-30 | 2016-10-06 | D-Vision C.V.S Ltd | Method and apparatus for monitoring changes in road surface condition |
Also Published As
| Publication number | Publication date |
|---|---|
| AU2018256505A1 (en) | 2019-07-04 |
| WO2019124668A1 (en) | 2019-06-27 |
| KR101969842B1 (en) | 2019-04-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10719720B2 (en) | Artificial intelligence system for providing road surface risk information and method thereof | |
| AU2018256505B2 (en) | Artificial intelligence system for providing road surface risk information and method thereof | |
| CN109584578B (en) | Method and device for recognizing a driving lane | |
| CN106043293B (en) | Method and device for safely parking a vehicle | |
| CN109641589B (en) | Route planning for autonomous vehicles | |
| US11681294B2 (en) | Method and system for prediction of roadwork zone | |
| CN107533800A (en) | Cartographic information storage device, automatic Pilot control device, control method, program and storage medium | |
| US10338598B2 (en) | Method for operating an automatically driven, driverless motor vehicle and monitoring system | |
| JP6069650B2 (en) | Traffic sign recognition method | |
| US11322025B2 (en) | Method and system for validating existence of roadwork | |
| US20090138497A1 (en) | Method and system for the use of probe data from multiple vehicles to detect real world changes for use in updating a map | |
| JP2006208223A (en) | Vehicle position recognition device and vehicle position recognition method | |
| US11531348B2 (en) | Method and apparatus for the detection and labeling of features of an environment through contextual clues | |
| US11501463B2 (en) | Method and apparatus for localization of position data | |
| EP2159777A2 (en) | Data mining to identify locations of potentially hazardous conditions for vehicle operation and use thereof | |
| CN114729803A (en) | Updating map data | |
| WO2020261567A1 (en) | Road surface inspection device, road surface inspection method, and program | |
| US20230042735A1 (en) | System for Determining Road Slipperiness in Bad Weather Conditions | |
| WO2020139356A1 (en) | Image pre-processing in a lane marking determination system | |
| JP4522387B2 (en) | Image recognition device | |
| KR102026686B1 (en) | Apparatus for providing dangerous road information using connected car and server for generating deep-learning model | |
| CN116457800A (en) | Architecture for map change detection in an autonomous vehicle | |
| WO2015173081A1 (en) | Method and apparatus for providing information data about entities along a route taken by a vehicle | |
| KR102018582B1 (en) | The apparatus and method for each lane collecting traffic information | |
| US20230048304A1 (en) | Environmentally aware prediction of human behaviors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGA | Letters patent sealed or granted (standard patent) |